English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Query Optimization remains an open problem for Big Data Management Systems.Traditional optimizers are cost-based and use statistical estimates ofintermediate result cardinalities to assign costs and pick the best plan.However, such estimates tend to become less accurate because of filteringconditions caused either from undetected correlations between multiplepredicates local to a single dataset, predicates with query parameters, orpredicates involving user-defined functions (UDFs). Consequently, traditionalquery optimizers tend to ignore or miscalculate those settings, thus leading tosuboptimal execution plans. Given the volume of today's data, a suboptimal plancan quickly become very inefficient.  In this work, we revisit the old idea of runtime dynamic optimization andadapt it to a shared-nothing distributed database system, AsterixDB. Theoptimization runs in stages (re-optimization points), starting by firstexecuting all predicates local to a single dataset. The intermediate resultcreated from each stage is used to re-optimize the remaining query. Thisre-optimization approach avoids inaccurate intermediate result cardinalityestimations, thus leading to much better execution plans. While it introducesthe overhead for materializing these intermediate results, our experiments showthat this overhead is relatively small and it is an acceptable price to paygiven the optimization benefits. In fact, our experimental evaluation showsthat runtime dynamic optimization leads to much better execution plans ascompared to the current default AsterixDB plans as well as to plans produced bystatic cost-based optimization (i.e. based on the initial dataset statistics)and other state-of-the-art approaches.

Revisiting Runtime Dynamic Optimization for Join Queries in Big Data Management Systems